State Coherence & Persistence
Structured state stores with formal contracts ensuring deterministic reliability. Without coherent state, generated software would be dream-like — vivid but inconsistent.
Current Frontier
Formal state contracts: typed, versioned state schemas that the world model must respect.
Key Questions
Can a single world model maintain coherent state across arbitrarily complex interactions?
How do you detect and recover from state drift in continuous generation?
Key Papers
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Chen et al.
Variable-horizon coherence without catastrophic drift
PERSIST: Persistent 3D World Generation
March 2026
Persistent 3D state in latent space, camera as query, geometric consistency by construction. THE most important paper for state coherence.
StateSpaceDiffuser
NeurIPS 2025
+14dB PSNR over DIAMOND, 50-step coherence vs 4-step via dual SSM+diffusion architecture.
EDELINE: SSM World Models
NeurIPS 2025
Replaces DIAMOND's LSTM with Mamba SSM for immediate coherence gains.
Self Forcing
NeurIPS 2025 Spotlight
Solves autoregressive drift by training on self-generated outputs. Directly attacks state drift.
MultiGen: Memory for Diffusion Game Engines
March 2026
External memory for diffusion game engines. Decomposes into Memory + Observation + Dynamics modules.
Long-Context SSM Video World Models
ICCV 2025
Block-wise SSM extends temporal memory beyond attention windows.
DreamerV3
Nature 2025
General world model maintaining state across 150+ diverse tasks with single config.
Current Insights
Separating state management from generation may be the key. The world model reads from and writes to a canonical state store, rather than maintaining state implicitly.
State contracts act as guardrails — the model can generate freely within the constraints of the contract, ensuring consistency.